Method and device for controlling a cruise control system of a self-driving vehicle

Abstract

The invention relates to a method and a device for controlling a cruise control system of a self-driving vehicle, comprising the following steps: - receiving (201) at least one set of information relating to a characterisation of the road along the future trajectory; - for each distance, o determining (202) a road type from the set of data characterising a road type; o determining (203) a curvature threshold according to the road type; o determining (204) a corrected curvature according to the curvature of the road and the curvature threshold, the corrected curvature being equal to 0 when the curvature of the road is less than the curvature threshold; - determining (205) a set of corrected curvatures from the set of corrected curvatures for each distance; and - transmitting (206) the set of corrected curvatures.

Description

DESCRIPTION TITLE: Method and device for controlling a cruise control system for an autonomous vehicle The present invention claims priority from French application 2308361 filed on 02.08.2023, the content of which (text, drawings and claims) is incorporated herein by reference. Technical field of the invention

[0001] The invention relates to the field of autonomous vehicle driving assistance systems. In particular, the invention relates to controlling a cruise control system for an autonomous vehicle. State of the art

[0002] A "vehicle" means any type of vehicle such as a motor vehicle, a moped, a motorcycle, a storage robot in a warehouse, etc. "Autonomous driving" of a "vehicle" means any process capable of assisting the driving of the vehicle; the "vehicle" is then also called an "autonomous vehicle". The process may therefore consist of partially or totally steering the vehicle or providing any type of assistance to a natural person driving the vehicle. The process thus covers all autonomous driving, from level 0 to level 5 in the OICA scale, for International Organization of Motor Vehicle Manufacturers.

[0003] Systems that assist vehicle driving are also called ADAS (Advanced Driver Assistance Systems), ADAS systems, or driver assistance systems. A vehicle's cruise control systems are part of ADAS systems and are well known. The vehicle's speed is regulated to a set speed without the driver having to press the accelerator pedal.

[0004] It is also known to automatically modify the set speed when the vehicle is cornering for comfort and safety reasons. For this, for example, a navigation system, including a geolocation system associated with mapping, can provide road characteristics.

[0005] The navigation system determines, over a horizon, the future trajectory of the vehicle on a road on which the vehicle is traveling. The horizon is understood as the total length or distance of the determined trajectory. For example, this total distance is between approximately 20 and 200 meters.

[0006] On this horizon, the mapping is able to provide a set of information relating to a characterization of said road along the future trajectory. This set of information is provided at different relative distances from the vehicle, for example every 1 meter or when data characterizing the road changes, the data being able to be a curvature of the road, a location of road sign, the start of a roundabout, data characterizing a road type such as a road shape and a road functionality class... "Curvature of the road at a location on the road", also called "curvature", means the inverse of a radius of curvature of the road at that location.

[0007] Vehicle cruise control systems that modify the set speed when the vehicle is cornering for comfort and safety purposes receive a set of curvatures along the trajectory. The vehicle cruise control system is said to be curvature-driven. Typically, a modified set speed at one point on the road is close to where y is a desired maximum transverse acceleration and where R is a radius of curvature (therefore the inverse of the curvature) at this location on the road.

[0008] This set of curvature provided to the cruise control system is quite large, and involves many calculations, sometimes unnecessary, by the cruise control. Indeed, for example on a highway, in a straight line, at each traffic sign a curvature close to 0 is sent. When cornering, since the design of the turns is based on clothoids, the curvatures change continuously, it is not easy to find a speed to pass through the bend. Summary of the invention

[0009] An object of the present invention is to remedy the aforementioned problem, in particular to optimize the transmission, to the cruise control, of the curvatures of a road along a trajectory determined by a navigation system, and to limit the calculations by a cruise control system modifying a set speed when the vehicle is turning for comfort and safety purposes.

[0010] To this end, a first aspect of the invention relates to a method for controlling a cruise control system of an autonomous vehicle, said vehicle traveling on a lane of a road, a navigation system determining, on a horizon, a future trajectory of said vehicle on said road, said method being implemented by a processor and comprising the steps of: • Receiving at least one set of information relating to a characterization of said road along the future trajectory, each set comprising a distance from said vehicle, a set of data characterizing a type of road at said distance, a curvature of said road at said distance, a type of road categorizing a road according to a reference speed and its accesses; • For each distance, o Determination of a road type from said set of data characterizing a road type; o Determination of a curvature threshold as a function of the road type; o Determination of a corrected curvature as a function of said road curvature and said curvature threshold, said corrected curvature being equal to 0 when said road curvature is less than said curvature threshold; • Determination of a set of corrected curvatures from the set of each corrected curvature for each distance; • Transmission of said set of corrected curvatures to said speed regulator, said speed regulator modifying a regulation setpoint speed as a function of the corrected curvatures.

[0011] Thus, the set speed of the vehicle cruise control is a function of a set of corrected curvatures. A certain number of said set of corrected curvatures along the trajectory become identical and zero. This simplifies the calculations. Also, the set speed is then a function of the road type, allowing, for example, to have higher curvature thresholds in certain situations and thus increase the number of corrected curvatures equal to 0.

[0012] Advantageously, two categories of road type are determined, a first category bringing together roads of a type similar to a motorway, a second category bringing together other types of road, said curvature threshold determined for the first category of road type being lower than said curvature threshold determined for the second category of road type.

[0013] This avoids having to calibrate too many thresholds per road type. It has been found useful to have at least one different threshold between roads of a type similar to a motorway and other road types.

[0014] Advantageously, the set of data characterizing a type of road at said distance comprises: • data characterizing a form of the road, the form of the road being at least a motorway or expressway excluding access or exit roads, or another form of road; and • data characterizing a class of functionality of the road, the class of functionality being at least a high-traffic road with a speed limit greater than substantially 80% of a maximum traffic speed of a country in which said vehicle is traveling, or another class of functionality.

[0015] Thus, with navigation systems using low-resolution maps, called SD maps, from the English acronym "Simple Definition", a road type is determined more reliably. SD maps can only provide information by road and not by lane. This type of mapping can provide road shape information and feature class information.

[0016] Advantageously, highway-like roads are determined when • the shape of the road is a motorway or expressway excluding access or exit roads; and • the functionality class is a high-traffic road with a speed limit that is significantly higher than 80% of the maximum traffic speed of the country in which the vehicle is traveling.

[0017] Advantageously, said method further comprises a step of optimizing all of the corrected curvatures, said optimization reducing the number of data.

[0018] Advantageously, when said curvature of the road for a given distance is greater than or equal to said curvature threshold, said corrected curvature for said given distance is a function of the set, for each distance, of the curvatures of the road and the corrected curvatures.

[0019] This makes it possible to filter the corrected curvatures. This makes the variations in curvatures between two different distances smoother, and thus makes the variations in the set speed smoother. This also makes it possible to limit the possible values ​​of the corrected curvatures according to the chosen resolution.

[0020] A second aspect of the invention relates to a device comprising a vehicle speed control system, a navigation system, a memory associated with at least one processor configured to implement the method according to the first aspect of the invention.

[0021] The invention also relates to a vehicle comprising the device.

[0022] The invention also relates to a computer program comprising instructions which, when the program is executed by the device according to the second aspect of the invention, cause the latter to implement the method according to the first aspect of the invention. Brief description of the figures

[0023] Other characteristics and advantages of the invention will emerge from the description of the non-limiting embodiments of the invention below, with reference to the appended figures, in which:

[0024] [Fig. 1] schematically illustrates a device, according to a particular exemplary embodiment of the present invention.

[0025] [Fig. 2] schematically illustrates a method for controlling a cruise control of an autonomous vehicle, according to a particular exemplary embodiment of the present invention. Detailed description of the invention

[0026] The invention is described below in its non-limiting application to the case of an autonomous motor vehicle traveling on a road or on a traffic lane. Other applications such as a robot in a storage warehouse or a motorcycle on a country road are also conceivable.

[0027] Figure 1 shows an example of a device 101 included in the vehicle, in a network (“cloud”) or in a server. This device 101 can be used as a centralized device in charge of at least certain steps of the method described below with reference to Figure 2. In one embodiment, it corresponds to an autonomous driving computer.

[0028] In the present invention, the device 101 is included in the vehicle.

[0029] This device 101 can take the form of a box comprising printed circuits, any type of computer or even a mobile telephone (“smartphone”).

[0030] The device 101 comprises a random access memory 102 for storing instructions for the implementation by a processor 103 of at least one step of the method as described below. The device also comprises a mass memory 104 for storing data intended to be retained after the implementation of the method.

[0031] The device 101 may further comprise a digital signal processor (DSP) 105. This DSP 105 receives data to format, demodulate and amplify, in a manner known per se, this data.

[0032] The device 101 also comprises an input interface 106 for receiving the data implemented by the method according to the invention and an output interface 107 for transmitting the data implemented by the method according to the invention.

[0033] For example, the input interface 106 can receive the following data: position or geographical location of the vehicle, speed and / or acceleration of the vehicle, set or predetermined positions / speeds / accelerations, engine speed, position and / or travel of the clutch, brake and / or acceleration pedal, detection of other vehicles or objects, position or geographical location of the other vehicles or objects detected, speed and / or acceleration of the other vehicles or objects detected, operating states of sensors, confidence index of data originating from or processed by sensors and / or devices similar to the device 101. For example, the sensors capable of providing data are: GPS associated or not with mapping, tachometers, accelerometers, RADAR, LIDAR, lasers, ultrasound, camera, navigation system, etc.

[0034] The input interface 106 can also receive the following data: a future trajectory of the vehicle, at least one set of information relating to a characterization of said road along the future trajectory, each set comprising a distance from said vehicle, a set of data characterizing a type of road at said distance, a curvature of said road at said distance, data characterizing a shape of the road, data characterizing a class of functionality of the road, ...

[0035] For example, the output interface 107 can transmit data similar to the data received by the input interface 106. Also, the output interface 107 can transmit: at least one road type, at least one curvature threshold, at least one corrected curvature, a set of corrected curvatures, a road type category gathering roads of a type similar to a highway, a road type category grouping together other road types, a set of optimized corrected curvatures, ...

[0036] [Fig. 2] schematically illustrates a method 200 for controlling a cruise control of an autonomous vehicle, according to a particular exemplary embodiment of the present invention.

[0037] The said vehicle travels on one lane of a road. A road allows the movement of vehicles between two given geographical points. A road comprises at least one carriageway, a part reserved for the movement of vehicles. A roadway comprises at least one lane, a part generally designed to be one-way.

[0038] A navigation system determines, over a horizon, a future trajectory of said vehicle on said road. A navigation system generally includes a geolocation system, such as a GPS, associated with a map, a database. For reasons, mainly, of memory capacity limitation, so-called low-resolution maps, called SD maps, from the English acronym "Simple Definition", are used. These types of maps are configured to provide characteristics at the level of a road. These types of maps cannot provide information for a specific lane of a road.

[0039] Said method is implemented by the processor 103 and comprises several steps.

[0040] Step 201, Rx, is a step of receiving at least one set of information relating to a characterization of said road along the future trajectory, each set comprising a distance relative to said vehicle, a set of data characterizing a type of road at said distance, a curvature of said road at said distance, a type of road categorizing a road according to a reference speed and its accesses.

[0041] For example, said at least one set of information relating to a characterization of said route along the future trajectory may be transmitted by said navigation system. Other devices similar to the device 101 may transmit this information.

[0042] For example, said at least one set of information relating to a characterization of said road along the future trajectory may be a matrix which, for each column, indicates, per row, a distance from said vehicle, a set of data characterizing a type of road, a curvature of said road. A type of road categorizes a road according to a reference speed and its accesses. A reference speed may be a maximum regulatory speed, an authorized speed limit, a practiced speed, ... an access may be with or without resident access, that is to say with or without controlled access (toll for example), or a grade-separated intersection or roundabout or plane, ...

[0043] In one operating mode, the data set characterizing a type of road at said distance includes: data characterizing a form of the road, the form of the road being at least a motorway or expressway excluding access or exit roads, or another form of road; and • data characterizing a functionality class of the road, the functionality class being at least a high-traffic road with a speed limit greater than approximately 80% of a maximum traffic speed of a country in which said vehicle is traveling, or another functionality class.

[0044] For example, the said other form of road includes a single-lane road, a roundabout, a junction... For example, in France, approximately 80% of a maximum traffic speed is in the order of 100 km / h.

[0045] A curvature of a road at a location, curvature, or curvature of the road at a location on the road, also called "curvature", is the inverse of a radius of curvature of the road at that location.

[0046] Step 202, DetTypRd, is a step, for each distance, of determining a road type from said set of data characterizing a road type. Thus, along the future trajectory, at different distances, the road type is known, a road type categorizing a road according to a reference speed and its accesses.

[0047] Advantageously, two categories of road type are determined, a first category bringing together roads of a type similar to a motorway, a second category bringing together other types of road, said curvature threshold determined for the first category of road type being lower than said curvature threshold determined for the second category of road type. Roads similar to a motorway are roads with potentially high traffic speeds and access to which is regulated because they are priority roads and without roundabouts or plan.

[0048] Advantageously, highway-like roads are determined when: • the shape of the road is a motorway or expressway excluding access or exit roads; and • the functionality class is a high-traffic road with a speed limit that is significantly higher than 80% of the maximum traffic speed of the country in which the vehicle is traveling.

[0049] The combination of these two criteria makes it possible to reliably determine whether a road is similar to a motorway. Indeed, SD maps contain inaccuracies or errors. One source of these inaccuracies or errors is that these maps are not updated often (at best every 6 months, generally every 12 months). If the road network changes, the map no longer accurately represents the current state of the road network.

[0050] Step 203, DetCurv, is a step, for each distance, of determining a curvature threshold depending on the type of road. It is then possible to have different thresholds. We adapt according to the situation. For example, for the first road category, it is interesting to have a lower threshold than for the second category. It has been found that having different thresholds allows for a smoother, more comfortable and more suitable variation of the cruise control set speed for a vehicle driver when traveling at a speed close to the road speed limit.

[0051] For example, for the first category of road type, the curvature threshold is in the order of 0.00030 rrr 1 and 0.00070 nr 1 , preferably close to 0.0006 rrr 1 but other values ​​are possible. For the second category of road type, the curvature threshold is of the order of 0.00080 rrr1 et 0.00150 nr 1 , preferably close to 0.00120 rrr 1 but other values ​​are possible.

[0052] Step 204, DetCurvC, is a step, for each distance, of determining a corrected curvature as a function of said road curvature and said curvature threshold, said corrected curvature being equal to 0 when said road curvature is less than said curvature threshold. Depending on the type of road, curvature values ​​of little use are replaced by 0.

[0053] Step 205, Optim, is a step of determining a set of corrected curvatures from the set of each corrected curvature for each distance. In step 206, this set is transmitted to said speed regulator.

[0054] Advantageously, said method further comprises a step of optimizing all of the corrected curvatures, said optimization reducing the number of data.

[0055] Taking the example above where said at least one set of information relating to a characterization of said road along the future trajectory is a matrix which, for each column, indicates, by row, a distance from said vehicle, a set of data characterizing a type of road, a curvature of said road, said set of corrected curvatures can be another matrix which, for each column, indicates, by row, a distance from said vehicle, and said corrected curvature.

[0056] In this example, furthermore, the dimension of said other matrix can be reduced and removing the curvature duplicates (same curvature value between two successive distances). This simplifies the calculations for a re-regulation setpoint speed calculation.

[0057] Advantageously, when said curvature of the road for a given distance is greater than or equal to said curvature threshold, said corrected curvature for said given distance is a function of the set, for each distance, of the curvatures of the road and the corrected curvatures. Thus, the curvatures are smoothed.

[0058] It is also possible to set a curvature resolution per curvature range, such as a resolution of 0.0001 rrr 1 for curvatures ranging from 0 to 0.0008 nr 1 , example a resolution of 0.0002 rrr 1 for curvatures ranging from 0.0008 to 0.0015 nr 1 , ... This limits the number of values ​​and simplifies the calculations.

[0059] Finally, step 206, TX, is a step of transmitting said set of corrected curvatures to said cruise control, said cruise control modifying a regulation setpoint speed as a function of the corrected curvatures. The cruise control receiving this list of corrected curvatures will adapt the setpoint speed as a function of a speed of the vehicle and the corrected curvatures received, making it possible to maximize the comfort of the vehicle's passengers and to maximize safety according to the type of road.

[0060] The present invention is not limited to the embodiments described above as examples: it extends to other variants.

[0061] For example, the process has been described according to a sequence of steps. Some steps can be carried out in parallel or according to another sequence.

Claims

CLAIMS 1. Method for controlling a cruise control system of an autonomous vehicle, said vehicle traveling on a lane of a road, a navigation system determining, on a horizon, a future trajectory of said vehicle on said road, said method being implemented by a processor (103) and comprising the steps of: • Reception (201) of at least one set of information relating to a characterization of said road along the future trajectory, each set comprising a distance relative to said vehicle, a set of data characterizing a type of road at said distance, a curvature of said road at said distance, a type of road categorizing a road according to a reference speed and its accesses; • For each distance, o Determination (202) of a road type from said set of data characterizing a road type; o Determination (203) of a curvature threshold as a function of the road type; o Determination (204) of a corrected curvature as a function of said road curvature and said curvature threshold, said corrected curvature being equal to 0 when said road curvature is less than said curvature threshold; • Determination (205) of a set of corrected curvatures from the set each corrected curvature for each distance; • Transmission (206) of said set of corrected curvatures to said speed regulator, said speed regulator modifying a regulation setpoint speed as a function of the corrected curvatures.

2. Method according to claim 1, in which two categories of road type are determined, a first category bringing together roads of a type similar to a motorway, a second category bringing together other types of road, said curvature threshold determined for the first category of road type being lower than said curvature threshold determined for the second category of road type.

3. Method according to any one of the preceding claims, in which the set of data characterizing a type of road at said distance comprises: • data characterizing a form of the road, the form of the road being at least a motorway or expressway excluding access or exit roads, or another form of road; and • data characterizing a functionality class of the road, the functionality class being at least one high-traffic road with a speed limit greater than substantially 80% of a traffic speed maximum of a country in which the said vehicle is circulated, or another functionality class.

4. Method according to claims 2 and 3, wherein the roads of a type similar to a motorway are determined when • the shape of the road is a motorway or expressway excluding access or exit roads; and • the functionality class is a high-traffic road with a speed limit that is significantly higher than 80% of the maximum traffic speed of the country in which the vehicle is traveling.

5. Method according to any one of the preceding claims, wherein said method further comprises a step of optimizing the set of corrected curvatures, said optimization reducing the number of data.

6. Method according to any one of the preceding claims, wherein when said curvature of the road for a given distance is greater than or equal to said curvature threshold, said corrected curvature for said given distance is a function of the set, for each distance, of the curvatures of the road and the corrected curvatures.

7. Device (101) comprising a vehicle speed control system, a navigation system, a memory (102) associated with at least one processor (103) configured to implement the method according to one of the preceding claims.

8. Vehicle comprising the device according to the preceding claim.

9. Computer program comprising instructions which, when the program is executed by the device (101) according to claim 7, cause the latter to implement the method according to one of claims 1 to 6.

Images